Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    python list dictionary Google Form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atera
    0.39
    <unused13>
    0.39
    $.\\
    0.39
    button
    0.36
    ether
    0.36
    ”
    0.36
    `
    0.35
    attribute
    0.35
    kara
    0.34
    ANY
    0.33
    POSITIVE LOGITS
     tyme
    0.47
     timeframe
    0.46
     अवधि
    0.42
     якщо
    0.42
     यदि
    0.42
     طول
    0.42
     μαγγ
    0.41
     אם
    0.41
    Mie
    0.41
    ᄄ
    0.41
    Act Density 0.000%

    No Known Activations